© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 17870
    Prev
    Next
    INDEX
    Explanations

    the word "it"

    oai_token-act-pair · gpt-3.5-turbo

    the word "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sheer
    -0.66
    EStream
    -0.66
    ¥ŀ
    -0.65
    SPONSORED
    -0.65
    ´
    -0.65
    Ļ½
    -0.65
    KER
    -0.64
     destro
    -0.63
    idth
    -0.62
    NetMessage
    -0.60
    POSITIVE LOGITS
    amins
    1.10
    uary
    1.06
    chell
    1.04
    anium
    0.95
    ocracy
    0.92
    rogen
    0.90
    igation
    0.88
    chers
    0.88
    ople
    0.87
    ivities
    0.85
    Activations Density 0.048%

    No Known Activations